Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaowu, Zhao, Hongfei, Hou, Jingyi, Liu, Zhijie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.07661
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910908346793984
author Zhang, Xiaowu
Zhao, Hongfei
Hou, Jingyi
Liu, Zhijie
author_facet Zhang, Xiaowu
Zhao, Hongfei
Hou, Jingyi
Liu, Zhijie
contents The Chinese Spelling Correction (CSC) task focuses on detecting and correcting spelling errors in sentences. Current research primarily explores two approaches: traditional multimodal pre-trained models and large language models (LLMs). However, LLMs face limitations in CSC, particularly over-correction, making them suboptimal for this task. While existing studies have investigated the use of phonetic and graphemic information in multimodal CSC models, effectively leveraging these features to enhance correction performance remains a challenge. To address this, we propose the Multimodal Analysis for Character Usage (\textbf{MACU}) experiment, identifying potential improvements for multimodal correctison. Based on empirical findings, we introduce \textbf{NamBert}, a novel multimodal model for Chinese spelling correction. Experiments on benchmark datasets demonstrate NamBert's superiority over SOTA methods. We also conduct a comprehensive comparison between NamBert and LLMs, systematically evaluating their strengths and limitations in CSC. Our code and model are available at https://github.com/iioSnail/NamBert.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07661
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unveiling the Impact of Multimodal Features on Chinese Spelling Correction: From Analysis to Design
Zhang, Xiaowu
Zhao, Hongfei
Hou, Jingyi
Liu, Zhijie
Computation and Language
The Chinese Spelling Correction (CSC) task focuses on detecting and correcting spelling errors in sentences. Current research primarily explores two approaches: traditional multimodal pre-trained models and large language models (LLMs). However, LLMs face limitations in CSC, particularly over-correction, making them suboptimal for this task. While existing studies have investigated the use of phonetic and graphemic information in multimodal CSC models, effectively leveraging these features to enhance correction performance remains a challenge. To address this, we propose the Multimodal Analysis for Character Usage (\textbf{MACU}) experiment, identifying potential improvements for multimodal correctison. Based on empirical findings, we introduce \textbf{NamBert}, a novel multimodal model for Chinese spelling correction. Experiments on benchmark datasets demonstrate NamBert's superiority over SOTA methods. We also conduct a comprehensive comparison between NamBert and LLMs, systematically evaluating their strengths and limitations in CSC. Our code and model are available at https://github.com/iioSnail/NamBert.
title Unveiling the Impact of Multimodal Features on Chinese Spelling Correction: From Analysis to Design
topic Computation and Language
url https://arxiv.org/abs/2504.07661